Venue-Influence Language Models for Expert Finding in Bibliometric Networks

Abstract

This article investigates the fundamental problem of traditional language models used for expert finding in bibliometric networks. It introduces novel Venue-Influence Language Modeling methods based on entropy, which can accommodate citation links based weights in an indirect way without using links information. Intuitively, an author publishing in topic-specific venues, either journals or for conferences, will be an expert on a topic as compared to an author publishing in multi-topic venues. The proposed methods are evaluated on real world data, the Digital Bibliography and Library Project (DBLP) dataset to test the performance. Experimental results show that their proposed venue influence language models (ViLMs) based methods outperform the traditional (non-venue based) language models (LM).

Analysis of public reactions to the novel Coronavirus (COVID-19) outbreak on Twitter

“…Essentially, low scores are assigned to noun phrases if their co-occurrences with other noun phrases follow a more or less random pattern, while a high relevance score is given to noun phrases that co-occur mainly with a limited set of other noun phrases. VOSviewer can be used to visualize a co-occurrence network of these terms ( Van Eck and Waltman, 2018) with high accuracy while removing manual text analysis expectation biases (Al- Barakati and Daud, 2018). This feature of VOSviewer helped us to mine the most trending tweet stories in the data set of tweets collected for this study.…”